{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:27Z","timestamp":1776887847371,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404828","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"436-443","source":"Crossref","is-referenced-by-count":147,"title":["The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Yoshioka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobutaka","family":"Ito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masakiyo","family":"Fujimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengzhu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wojciech J.","family":"Fabian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miquel","family":"Espi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Higuchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495994"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959513"},{"key":"ref30","first-page":"953","article-title":"An EM algorithm for localizing multiple sound sources in reverberant environments","volume":"13","author":"mandel","year":"2007","journal-title":"Adv Neural Inform Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref35","article-title":"Robust MVDR beamforming using time-frequency masks for on-line\/offline ASR in noise","author":"higuchi","year":"2016","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954300"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045183"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854829"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent pretrained deep neural networks for large-vocabulary speech recognition","volume":"20","author":"dahl","year":"2012","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"ref15","author":"yu","year":"2014","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref4","article-title":"The third ‘CHiME’ speech separation and recognition challenge: dataset, task and baselines","author":"barker","year":"2015","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854660"},{"key":"ref3","article-title":"The MERL\/MELCO\/TUM system for the REVERB challenge using deep recurrent neural network feature enhancement","author":"weninger","year":"2014","journal-title":"Proc REVERB Workshop"},{"key":"ref6","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel?","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2263137"},{"key":"ref5","article-title":"Kaldi","year":"0"},{"key":"ref8","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Network in network","author":"lin","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge","author":"delcroix","year":"2014","journal-title":"Proc REVERB Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638967"},{"key":"ref1","first-page":"19","article-title":"Discriminative methods for noise robust speech recognition: a CHiME challenge benchmark","author":"tachioka","year":"2013","journal-title":"International Workshop on Machine Listening in Multisource Environments"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"605","DOI":"10.21437\/Interspeech.2011-242","article-title":"Empirical evaluation and combination of advanced language modeling techniques","author":"mikolov","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.008"},{"key":"ref23","article-title":"RNNLM toolkit","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2006.270881"},{"key":"ref25","first-page":"359","article-title":"A new method based on spectral subtraction for speech dereverberation","volume":"87","author":"lebart","year":"2001","journal-title":"Acta Acustica United with Acustica"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","location":"Scottsdale, AZ, USA","start":{"date-parts":[[2015,12,13]]},"end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404828.pdf?arnumber=7404828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,4]],"date-time":"2022-06-04T01:23:58Z","timestamp":1654305838000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404828","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}